Toxicity Prediction Of Compounds In Cellular Structures

Abstract

Methods, apparatus and systems are disclosed for predicting toxicity of one or more compounds applied to a plurality of samples of a cellular structure in an in-vitro microscopy assay. A set of images associated with the plurality of samples are received. Each image of the set of images are input to a first ML model configured for predicting phenotype features of the cellular structure within the sample associated with said each image. Each of the predicted phenotype features associated with each sample are input to a second ML model configured for predicting a lower dimensional phenotype feature embedding of said each sample. The distance between the lower dimensional phenotype feature embedding of said each sample is compared with that of a sample applied with a compound having a known toxicity. For each sample, an indication of the toxicity of said each sample and applied compound thereto is output based on said comparison.

1 - 15 . (canceled) 
     
     
         16 . A computer-implemented method for predicting toxicity of one or more compounds applied to a plurality of samples of a cellular structure in an in-vitro microscopy assay, the method comprising:
 receiving a set of images associated with the plurality of samples;   inputting each image of the set of images to a first ML model configured for predicting phenotype features of the cellular structure within the sample associated with said each image;   inputting each of the predicted phenotype features associated with each sample to a second ML model configured for predicting a lower dimensional phenotype feature embedding of said each sample;   comparing the distance between the lower dimensional phenotype feature embedding of said each sample with that of a sample applied with a compound having a known toxicity; and   outputting, for each sample, an indication of the toxicity of said each sample and applied compound thereto based on said comparison.   
     
     
         17 . The computer-implemented method of  claim 16 , wherein the first ML model is a neural network or convolutional neural network, CNN, model, the neural network or CNN model is trained for classification using cellular image training data and the predicted phenotype features are embedded within a full layer of the trained neural network or CNN model, the method comprising outputting the phenotype feature embeddings from the full layer. 
     
     
         18 . The computer-implemented method  claim 16 , wherein the second ML model is based on a Uniform Manifold Approximation and Projection, UMAP, algorithm or t-SNE algorithm for dimensional reduction of the phenotype feature embedding of a sample, wherein the phenotype feature embedding is mapped to a lower dimensional vector space for use in comparing the distance between the phenotype feature embedding and that of a sample with a compound having a known toxicity. 
     
     
         19 . The computer-implemented method of  claim 18 , further comprising:
 training the second ML model on the UMAP technique using unsupervised training based on negative and positive control samples of the plurality of samples for predicting a toxicity distance metric associated with the samples with compounds applied thereto having a known toxicity; or   training the second ML model comprises iteratively performing a grid search over a set of hyperparameters of the UMAP technique for selecting those hyperparameters that maximise the differences between the negative control samples and the positive control samples.   
     
     
         20 . The computer-implemented method of  claim 18 , wherein indicating the toxicity of the phenotype feature embedding of a sample with compound applied thereto comprises:
 applying the phenotype feature embedding of a sample with compound applied thereto to the second ML model for outputting a lower dimensional embedding of said sample with compound applied thereto; and   determining ( 325 ,  325   a,    325   b,    326 ) an indication of the toxicity of said sample with compound applied thereto based on comparing the distance between said lower dimensional embedding and the embeddings of one or more samples with compounds applied thereto having known toxicity.   
     
     
         21 . The computer-implemented method of  claim 18 , wherein indicating the toxicity of the phenotype feature embedding of a sample with compound applied thereto further comprises:
 applying the phenotype feature embedding of a sample with compound applied thereto to the second ML model for outputting a lower dimensional embedding of said sample with compound applied thereto; and   applying ( 324 ,  325 ) the lower dimensional embedding of said sample with compound applied thereto to a third ML model trained for outputting an indication of the distance between the lower dimensional embedding and a set of the lower dimensional embeddings associated with the negative control samples.   
     
     
         22 . The computer-implemented method of  claim 21 , further comprising training the third ML model based on performing a grid search over a set of hyperparameters of a high dimensional distance metric algorithm that maximise a distance between the lower dimensional embeddings of the negative control samples and the positive control samples, whilst minimising the distance between the lower dimensional embeddings of the negative control samples or minimising the distance between the lower dimensional embeddings of the positive control samples. 
     
     
         23 . The computer-implemented method of  claim 16 , wherein comparing the distance used for indicating the toxicity of the phenotype feature embedding of a sample is based on Wasserstein distance metrics. 
     
     
         24 . The computer-implemented method of  claim 16 , wherein receiving said set of images associated with the plurality of samples further comprises:
 identifying viable samples of cellular structures for analysis in an in-vitro microscopy assay, based on the steps of:   automatically identifying a first set of samples useful for analysis from a plurality of samples of an assay plate;   generating a set of 2-dimensional, 2D, images for each sample in the first set of samples, said set of 2D images for said each sample comprising multiple 2D image slices taken along a z-axis of said each sample; and   identifying from the sets of 2D image slices a set of viable samples; and   outputting data representative of said set of viable samples for analysis as the set of images.   
     
     
         25 . The computer-implemented method of  claim 24 , wherein automatically identifying a first set of samples further comprises, for each sample in the plurality of samples:
 pre-processing an image of said each sample;   inputting said pre-processed sample image to a first machine learning, ML, model configured for identifying a region of interest of the input sample image comprising a cellular structure;   inputting the identified region of interest of sample image to a second ML model configured for classifying whether said sample is analysable; and   outputting the first set of samples comprising data representative of those samples that are classified to be analysable.   
     
     
         26 . The computer-implemented method of  claim 25 , wherein:
 the first ML model for identifying the region of interest is a convolutional neural network, CNN, or other neural network trained for identifying regions of interest comprising cellular structures, and   the second ML model for classifying whether said sample is analysable is a one class SVM configured to classify whether said region of interest is analysable.   wherein:   training/configuring the CNN based on a labelled training dataset, said labelled training dataset comprising a plurality of images, each of the images annotated with a label comprising data representative of whether a cellular region of interest is present, and/or the location of the region of interest within the image; and   training/configuring the one class SVM to classify whether said region of interest is analysable.   
     
     
         27 . The computer-implemented method of  claim 24 , wherein identifying from the sets of 2D image slices the set of viable samples further comprises, for each sample:
 identifying foreground, background and multiple uncertain feature areas of the cellular structure in each of the 2D image slices;   iteratively combining the foreground, background and uncertain feature areas of the 2D image slices to generate a single 2D image of the cellular structure; and   selecting the sample for the viable sample set based on the quality of the single 2D image; and   outputting a set of viable images for each selected sample comprising image data representative of the single 2D images associated with each selected sample;   wherein the multiple uncertain feature areas comprise multiple uncertain foreground features and multiple uncertain background features.   
     
     
         28 . An apparatus comprising a processor, a memory unit and a communication interface, wherein the processor is connected to the memory unit and the communication interface, wherein the processor and memory are configured to implement operations for predicting toxicity of one or more compounds applied to a plurality of samples of a cellular structure in an in-vitro microscopy assay, the operations comprising:
 receiving a set of images associated with the plurality of samples;   inputting each image of the set of images to a first ML model configured for predicting phenotype features of the cellular structure within the sample associated with said each image;   inputting each of the predicted phenotype features associated with each sample to a second ML model configured for predicting a lower dimensional phenotype feature embedding of said each sample;   comparing the distance between the lower dimensional phenotype feature embedding of said each sample with that of a sample applied with a compound having a known toxicity; and   outputting, for each sample, an indication of the toxicity of said each sample and applied compound thereto based on said comparison.   
     
     
         29 . The apparatus of  claim 28 , wherein the first ML model is a neural network or convolutional neural network, CNN, model, the neural network or CNN model is trained for classification using cellular image training data and the predicted phenotype features are embedded within a full layer of the trained neural network or CNN model, the operations comprising outputting the phenotype feature embeddings from the full layer. 
     
     
         30 . The apparatus of  claim 28 , wherein the second ML model is based on a Uniform Manifold Approximation and Projection, UMAP, algorithm or t-SNE algorithm for dimensional reduction of the phenotype feature embedding of a sample, wherein the phenotype feature embedding is mapped to a lower dimensional vector space for use in comparing the distance between the phenotype feature embedding and that of a sample with a compound having a known toxicity. 
     
     
         31 . The apparatus of  claim 30 , the operations further comprising:
 training the second ML model on the UMAP technique using unsupervised training based on negative and positive control samples of the plurality of samples for predicting a toxicity distance metric associated with the samples with compounds applied thereto having a known toxicity; or   training the second ML model comprises iteratively performing a grid search over a set of hyperparameters of the UMAP technique for selecting those hyperparameters that maximise the differences between the negative control samples and the positive control samples.   
     
     
         32 . The apparatus of  claim 30 , wherein indicating the toxicity of the phenotype feature embedding of a sample with compound applied thereto comprises:
 applying the phenotype feature embedding of a sample with compound applied thereto to the second ML model for outputting a lower dimensional embedding of said sample with compound applied thereto; and   determining ( 325 ,  325   a,    325   b,    326 ) an indication of the toxicity of said sample with compound applied thereto based on comparing the distance between said lower dimensional embedding and the embeddings of one or more samples with compounds applied thereto having known toxicity.   
     
     
         33 . The apparatus of  claim 30 , wherein indicating the toxicity of the phenotype feature embedding of a sample with compound applied thereto further comprises:
 applying the phenotype feature embedding of a sample with compound applied thereto to the second ML model for outputting a lower dimensional embedding of said sample with compound applied thereto; and   applying ( 324 ,  325 ) the lower dimensional embedding of said sample with compound applied thereto to a third ML model trained for outputting an indication of the distance between the lower dimensional embedding and a set of the lower dimensional embeddings associated with the negative control samples.   
     
     
         34 . A non-transitory computer-readable medium comprising data or instruction code, which when executed on a processor, causes the processor to implement operations for predicting toxicity of one or more compounds applied to a plurality of samples of a cellular structure in an in-vitro microscopy assay, the operations comprising:
 receiving a set of images associated with the plurality of samples;   inputting each image of the set of images to a first ML model configured for predicting phenotype features of the cellular structure within the sample associated with said each image;   inputting each of the predicted phenotype features associated with each sample to a second ML model configured for predicting a lower dimensional phenotype feature embedding of said each sample;   comparing the distance between the lower dimensional phenotype feature embedding of said each sample with that of a sample applied with a compound having a known toxicity; and   outputting, for each sample, an indication of the toxicity of said each sample and applied compound thereto based on said comparison.   
     
     
         35 . The non-transitory computer-readable medium of  claim 34 , wherein the first ML model is a neural network or convolutional neural network, CNN, model, the neural network or CNN model is trained for classification using cellular image training data and the predicted phenotype features are embedded within a full layer of the trained neural network or CNN model, the operations comprising outputting the phenotype feature embeddings from the full layer.